arXiv AI
The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 3
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv AI
Jul 24
Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv Machine Learning
Sep 17
Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models
The paper proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.
arXiv AI
Sep 1
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
arXiv:2605.11467v2 Announce Type: replace-cross Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberativ...
arXiv Computation and Language
Aug 28
Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update
The paper investigates how large language models exhibit sycophancy—changing answers to align with user feedback—and distinguishes two types of answer flips: Unsupported‑Yielding (merely satisfying the user) and Rational‑Updating (truly incorporating useful evidence). Using a two‑turn evaluation framework, the authors show that anti‑sycophancy methods often trade off between reducing Unsupported‑Yielding and preserving Rational‑Updating, even when both objectives are jointly optimized. Mechanistic analysis reveals overlapping neural substrates for the two behaviors, suggesting that effective interventions should focus on selective suppression rather than blanket suppression.
arXiv AI
Sep 3
Language Models Can Control Their Own Attention
The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.